Kalman Filter Engineering Assistant
Design, debug, and tune Kalman filters for robust state estimation
by myriadprotocolTechnology & SoftwareEngineeringGuidance, Navigation & Control EngineerKalman FilterWhat You Can Do
This skill guides you through designing Kalman filters for your specific state estimation and sensor fusion problems. You'll learn to diagnose filter divergence, tune covariance matrices (Q and R), and validate observability—turning mathematical theory into production-ready filters. The skill provides step-by-step workflows, diagnostic tools, and practical templates for common applications like GPS/IMU fusion, SLAM, and aircraft navigation.
Features
Create optimal state-space models for your estimation problem with process and measurement equations
Verify observability, controllability, and stability of your filter design
Structured methods to optimize Q (process noise) and R (measurement noise) matrices
Root-cause analysis for biased estimates, gain collapse, and instability
Multi-sensor integration with conflict detection and adaptive weighting
Whiteness testing and correlation checks to validate filter assumptions
Pre-built filters for constant-velocity, constant-acceleration, and AHRS applications
Verification steps and performance metrics before hardware integration
Example Output
Example 1: GPS/IMU Fusion Design Request
You ask: "Design a Kalman filter for GPS/IMU fusion. GPS accuracy ±5m at 1Hz, IMU at 100Hz with 0.5°/s gyro drift."
You get:
- 9-dimensional state vector: [position, velocity, attitude]
- Process noise Q matrix with gyro bias modeling
- Measurement noise R tuned to GPS/IMU uncertainties
- Initialization strategy and convergence criteria
- Innovation monitoring thresholds
Example 2: Debugging Divergence
You ask: "My filter diverges after 30 seconds. Q=0.01, R=0.1, innovations grow 5% per step."
You get:
- Root cause: Process model too confident (Q underestimated)
- Recommended Q adjustment: multiply by 10
- Innovation whiteness test showing lag-1 correlation
- Steady-state gain matrix and expected error
- Validation test to confirm fix
Example 3: Observability Analysis
You ask: "My 12-state INS filter won't converge to true attitude. States=[pos, vel, attitude, accel_bias]. Measurements=[position, velocity only]."
You get:
- Observability rank: 9/12 (3 states unobservable)
- Which states cannot be estimated from sensors
- Recommended additional sensors (magnetometer, altitude reference)
- Redesigned filter with observable subset
What's Included
- SKILL.md: Complete Kalman filter workflow with decision trees and structured guidance
- Filter Design Checklist: State vector, equations, noise modeling, initialization strategy
- Covariance Tuning Worksheet: Q and R matrix strategies with adjustment heuristics
- Convergence Diagnostic Guide: Innovation analysis, filter gain verification, divergence root causes
- Sensor Fusion Workflow: Multi-sensor integration, conflict detection, adaptive weighting
- Code Templates: Python/MATLAB pseudocode for constant-velocity, constant-acceleration, and AHRS filters
- Pre-Deployment Checklist: Final verification steps, performance metrics, production readiness
Who It's For
- Control systems engineers designing guidance, navigation, and control (GNC) systems for aircraft and vehicles
- Roboticists implementing SLAM, odometry fusion, and autonomous navigation algorithms
- Aerospace engineers developing state estimation for inertial navigation systems (INS) and sensor fusion
- Signal processing specialists working on time-series filtering, prediction, and state estimation
- Embedded systems engineers tuning resource-constrained filters for real-time applications
Best For
- Designing Kalman filters from scratch for a new state estimation or sensor fusion application
- Debugging filter divergence, instability, or biased estimates in existing implementations
- Tuning Q and R matrices to balance filter responsiveness, stability, and noise rejection
- Integrating multiple sensors (GPS, IMU, magnetometer, radar) with conflict detection and weighting
- Analyzing observability and controllability of filter designs before deployment
- Validating filter performance with diagnostic metrics and pre-deployment checklists
You might also like
Analyze Solidity and other smart contract code for security vulnerabilities, gas inefficiencies, and best practice violations. Get detailed reports with risk scoring, remediation suggestions, and optimization recommendations. Whether you're auditing before deployment or reviewing third-party contracts, this skill identifies critical issues faster than manual review.
You can systematically diagnose database performance bottlenecks by sharing your schema, slow query logs, and execution plans with Claude. It identifies root causes—missing indexes, inefficient joins, lock contention—and provides prioritized recommendations with ready-to-implement SQL. Skip the manual log analysis and get tuning strategies tailored to your workload.
This skill provides a structured approach to analyzing process problems, identifying root causes, and recommending capacity optimizations. You'll get clear bottleneck identification, data-driven recommendations, and a framework to validate whether your solutions actually work. Perfect for diagnosing why workflows are slow and finding the leverage points that matter most.
Use Claude to systematically analyze your database queries, execution plans, and schema to identify performance bottlenecks. The skill generates actionable optimization recommendations with SQL rewrites, index strategies, and configuration tuning. You'll receive detailed before-and-after performance analysis to validate improvements and prioritize work by impact.
You'll design and implement mobile features with architectural rigor, cross-platform considerations, and edge-case handling built-in. This skill generates complete system designs, platform-specific implementation strategies, performance optimization approaches, and testing frameworks. The output is production-ready guidance spanning iOS and Android with security, offline resilience, and deployment strategies included.
Design and optimize injectable formulations by analyzing your active pharmaceutical ingredient (API), selecting compatible excipients, and predicting stability outcomes. You'll receive systematic workflows that guide you through API characterization, formulation architecture, and risk mitigation—enabling faster development cycles and regulatory-ready documentation.
You'll develop systematic approaches to injectable formulation design, from API selection through sterilization strategy. Claude helps you troubleshoot failed batches by analyzing root causes, recommends regulatory pathways (505(b)(2), ANDA, NDA), and provides science-backed solutions for stability, compatibility, and manufacturability challenges.
You can architect multi-node ROS control systems from scratch, including node design patterns, communication flows, and real-time constraints. You'll debug complex node interactions using publisher/subscriber analysis, service call tracing, and action server diagnostics. You can optimize motion controllers through PID tuning, trajectory planning validation, and performance profiling to achieve precise, responsive robotic behavior.